From mboxrd@z Thu Jan 1 00:00:00 1970 From: Ashok Anand Subject: issue using SRIOV "Unable to start - perhaps the PF driver is not up yet", while PF driver is actually up Date: Mon, 10 Sep 2012 15:54:34 +0530 Message-ID: References: Mime-Version: 1.0 Content-Type: multipart/mixed; boundary="===============2699084713964537592==" Return-path: In-Reply-To: List-Unsubscribe: , List-Post: List-Help: List-Subscribe: , Sender: xen-devel-bounces@lists.xen.org Errors-To: xen-devel-bounces@lists.xen.org To: xen-devel@lists.xen.org List-Id: xen-devel@lists.xenproject.org --===============2699084713964537592== Content-Type: multipart/alternative; boundary=f46d04426d22348a2104c9565da8 --f46d04426d22348a2104c9565da8 Content-Type: text/plain; charset=ISO-8859-1 Hi, I am trying to use SRIOV, usnig xen 4.0 on debian. On my dom0, xm pci-list-assignable-devices show that 0000:0f:10.0 0000:0f:10.2 0000:0f:10.4 0000:0f:10.6 0000:0f:11.2 0000:0f:11.4 0000:0f:11.6 these virtual interfaces correspond to eth2, i attach 0f:10.0 to a domU ubuntu machine, xm pci-attach ubuntu 0f:10.0 on my dom0 machine, i can ping other machine using eth2, (implying PF on eth2 is active) on my domU machine, when i attach the virtual function, i get the following messages [ 2282.688356] ixgbevf 0000:00:00.0: Xen PCI mapped GSI0 to IRQ28 [ 2282.688470] ixgbevf 0000:00:00.0: setting latency timer to 64 [ 2282.690187] ixgbevf 0000:00:00.0: PF still in reset state, assigning new address while PF on eth2 is there and active, since i can ping other machine. Now, when I try to bring up the VF interface on domU, i get the following error 2476.295582] Unable to start - perhaps the PF Driver isn't up yet SIOCSIFFLAGS: Network is down [ 2476.296917] Unable to start - perhaps the PF Driver isn't up yet SIOCSIFFLAGS: Network is down and on dmesg on domU, [ 2476.295582] Unable to start - perhaps the PF Driver isn't up yet [ 2476.296917] Unable to start - perhaps the PF Driver isn't up yet Any thoughts on what could be wrong? I have been struggling with this for quite some time and would really appreciate your thoughts on it. Thanks, Ashok --f46d04426d22348a2104c9565da8 Content-Type: text/html; charset=ISO-8859-1 Content-Transfer-Encoding: quoted-printable
Hi,=A0

I am trying to use SRI= OV, usnig xen 4.0 on debian.=A0

On my dom0, xm pci= -list-assignable-devices show that
0000:0f:10.0
00= 00:0f:10.2
0000:0f:10.4
0000:0f:10.6
0000:0f:11.2
0000:0f:11.4
0= 000:0f:11.6

these virtual interfaces corresp= ond to eth2,=A0

i attach 0f:10.0 to a domU ubuntu = machine,=A0xm pci-attach ubuntu 0f:10.0

on my dom0 machine, i can ping other machine using eth2= , (implying PF on eth2 is active)

on my domU machi= ne, when i attach the virtual function, i get the following messages

[ 2282.688356] ixgbevf 0000:00:00.0: Xen PCI m= apped GSI0 to IRQ28
[ 2282.688470] ixgbevf 0000:00:00.0: sett= ing latency timer to 64
[ 2282.690187] ixgbevf 0000:00:00.0: PF still in reset state, assi= gning new address

while PF on eth2 is =A0there and active, since i = can ping other machine.

Now, when I try to bring u= p the VF interface on domU,=A0
=A0i get the following error
=

=A02476.295582] Unable to start - perhaps the PF Driver= isn't up yet
SIOCSIFFLAGS: Network is down
[ 2476.= 296917] Unable to start - perhaps the PF Driver isn't up yet
SIOCSIFFLAGS: Network is down

and on dmesg o= n domU,=A0
[ 2476.295582] Unable to start - perhaps the PF D= river isn't up yet
[ 2476.296917] Unable to start - perhaps t= he PF Driver isn't up yet


Any thoughts on what could be wron= g? I have been struggling with this for quite some time
and would= really appreciate your thoughts on it.

Thanks,=A0=
Ashok






--f46d04426d22348a2104c9565da8-- --===============2699084713964537592== Content-Type: text/plain; charset="us-ascii" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit Content-Disposition: inline _______________________________________________ Xen-devel mailing list Xen-devel@lists.xen.org http://lists.xen.org/xen-devel --===============2699084713964537592==-- From mboxrd@z Thu Jan 1 00:00:00 1970 From: Andrew Cooper Subject: Re: issue using SRIOV "Unable to start - perhaps the PF driver is not up yet", while PF driver is actually up Date: Mon, 10 Sep 2012 11:26:33 +0100 Message-ID: <504DC059.4070003@citrix.com> References: Mime-Version: 1.0 Content-Type: multipart/mixed; boundary="===============6736997857128962086==" Return-path: In-Reply-To: List-Unsubscribe: , List-Post: List-Help: List-Subscribe: , Sender: xen-devel-bounces@lists.xen.org Errors-To: xen-devel-bounces@lists.xen.org To: xen-devel@lists.xen.org List-Id: xen-devel@lists.xenproject.org --===============6736997857128962086== Content-Type: multipart/alternative; boundary="------------070502040207030606070503" --------------070502040207030606070503 Content-Type: text/plain; charset="ISO-8859-1" Content-Transfer-Encoding: 7bit On 10/09/12 11:24, Ashok Anand wrote: > Hi, > > I am trying to use SRIOV, usnig xen 4.0 on debian. > > On my dom0, xm pci-list-assignable-devices show that > 0000:0f:10.0 > 0000:0f:10.2 > 0000:0f:10.4 > 0000:0f:10.6 > 0000:0f:11.2 > 0000:0f:11.4 > 0000:0f:11.6 > > these virtual interfaces correspond to eth2, Are you sure? 0f:10.0 is probably the physical function which you must keep in dom0. ~Andrew > > i attach 0f:10.0 to a domU ubuntu machine, xm pci-attach ubuntu 0f:10.0 > > on my dom0 machine, i can ping other machine using eth2, (implying PF > on eth2 is active) > > on my domU machine, when i attach the virtual function, i get the > following messages > > [ 2282.688356 ] ixgbevf 0000:00:00.0: Xen PCI > mapped GSI0 to IRQ28 > [ 2282.688470 ] ixgbevf 0000:00:00.0: setting > latency timer to 64 > [ 2282.690187 ] ixgbevf 0000:00:00.0: PF still > in reset state, assigning new address > > while PF on eth2 is there and active, since i can ping other machine. > > Now, when I try to bring up the VF interface on domU, > i get the following error > > 2476.295582] Unable to start - perhaps the PF Driver isn't up yet > SIOCSIFFLAGS: Network is down > [ 2476.296917] Unable to start - perhaps the PF Driver isn't up yet > SIOCSIFFLAGS: Network is down > > and on dmesg on domU, > [ 2476.295582] Unable to start - perhaps the PF Driver isn't up yet > [ 2476.296917] Unable to start - perhaps the PF Driver isn't up yet > > > Any thoughts on what could be wrong? I have been struggling with this > for quite some time > and would really appreciate your thoughts on it. > > Thanks, > Ashok > > > > > > -- Andrew Cooper - Dom0 Kernel Engineer, Citrix XenServer T: +44 (0)1223 225 900, http://www.citrix.com --------------070502040207030606070503 Content-Type: text/html; charset="ISO-8859-1" Content-Transfer-Encoding: 7bit
On 10/09/12 11:24, Ashok Anand wrote:
Hi, 

I am trying to use SRIOV, usnig xen 4.0 on debian. 

On my dom0, xm pci-list-assignable-devices show that
0000:0f:10.0
0000:0f:10.2
0000:0f:10.4
0000:0f:10.6
0000:0f:11.2
0000:0f:11.4
0000:0f:11.6

these virtual interfaces correspond to eth2,

Are you sure?  0f:10.0 is probably the physical function which you must keep in dom0.

~Andrew


i attach 0f:10.0 to a domU ubuntu machine, xm pci-attach ubuntu 0f:10.0

on my dom0 machine, i can ping other machine using eth2, (implying PF on eth2 is active)

on my domU machine, when i attach the virtual function, i get the following messages

[ 2282.688356] ixgbevf 0000:00:00.0: Xen PCI mapped GSI0 to IRQ28
[ 2282.688470] ixgbevf 0000:00:00.0: setting latency timer to 64
[ 2282.690187] ixgbevf 0000:00:00.0: PF still in reset state, assigning new address

while PF on eth2 is  there and active, since i can ping other machine.

Now, when I try to bring up the VF interface on domU, 
 i get the following error

 2476.295582] Unable to start - perhaps the PF Driver isn't up yet
SIOCSIFFLAGS: Network is down
[ 2476.296917] Unable to start - perhaps the PF Driver isn't up yet
SIOCSIFFLAGS: Network is down

and on dmesg on domU, 
[ 2476.295582] Unable to start - perhaps the PF Driver isn't up yet
[ 2476.296917] Unable to start - perhaps the PF Driver isn't up yet


Any thoughts on what could be wrong? I have been struggling with this for quite some time
and would really appreciate your thoughts on it.

Thanks, 
Ashok







-- 
Andrew Cooper - Dom0 Kernel Engineer, Citrix XenServer
T: +44 (0)1223 225 900, http://www.citrix.com
--------------070502040207030606070503-- --===============6736997857128962086== Content-Type: text/plain; charset="us-ascii" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit Content-Disposition: inline _______________________________________________ Xen-devel mailing list Xen-devel@lists.xen.org http://lists.xen.org/xen-devel --===============6736997857128962086==-- From mboxrd@z Thu Jan 1 00:00:00 1970 From: Pasi =?iso-8859-1?Q?K=E4rkk=E4inen?= Subject: Re: issue using SRIOV "Unable to start - perhaps the PF driver is not up yet", while PF driver is actually up Date: Mon, 10 Sep 2012 13:27:37 +0300 Message-ID: <20120910102737.GG8912@reaktio.net> References: Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Return-path: Content-Disposition: inline In-Reply-To: List-Unsubscribe: , List-Post: List-Help: List-Subscribe: , Sender: xen-devel-bounces@lists.xen.org Errors-To: xen-devel-bounces@lists.xen.org To: Ashok Anand Cc: xen-devel@lists.xen.org List-Id: xen-devel@lists.xenproject.org On Mon, Sep 10, 2012 at 03:54:34PM +0530, Ashok Anand wrote: > Hi, > I am trying to use SRIOV, usnig xen 4.0 on debian. > On my dom0, xm pci-list-assignable-devices show that > 0000:0f:10.0 > 0000:0f:10.2 > 0000:0f:10.4 > 0000:0f:10.6 > 0000:0f:11.2 > 0000:0f:11.4 > 0000:0f:11.6 > these virtual interfaces correspond to eth2, > i attach 0f:10.0 to a domU ubuntu machine, xm pci-attach ubuntu 0f:10.0 > on my dom0 machine, i can ping other machine using eth2, (implying PF on > eth2 is active) > on my domU machine, when i attach the virtual function, i get the > following messages > [1][ 2282.688356] ixgbevf 0000:00:00.0: Xen PCI mapped GSI0 to IRQ28 > [2][ 2282.688470] ixgbevf 0000:00:00.0: setting latency timer to 64 > [3][ 2282.690187] ixgbevf 0000:00:00.0: PF still in reset state, assigning > new address > while PF on eth2 is there and active, since i can ping other machine. > Now, when I try to bring up the VF interface on domU, > i get the following error > 2476.295582] Unable to start - perhaps the PF Driver isn't up yet > SIOCSIFFLAGS: Network is down > [ 2476.296917] Unable to start - perhaps the PF Driver isn't up yet > SIOCSIFFLAGS: Network is down > and on dmesg on domU, > [ 2476.295582] Unable to start - perhaps the PF Driver isn't up yet > [ 2476.296917] Unable to start - perhaps the PF Driver isn't up yet > Any thoughts on what could be wrong? I have been struggling with this for > quite some time > and would really appreciate your thoughts on it. > Did you do "ifconfig ethX up" in dom0? -- Pasi From mboxrd@z Thu Jan 1 00:00:00 1970 From: Ashok Anand Subject: Re: issue using SRIOV "Unable to start - perhaps the PF driver is not up yet", while PF driver is actually up Date: Mon, 10 Sep 2012 16:04:01 +0530 Message-ID: References: <504DC059.4070003@citrix.com> Mime-Version: 1.0 Content-Type: multipart/mixed; boundary="===============3633803858675574930==" Return-path: In-Reply-To: <504DC059.4070003@citrix.com> List-Unsubscribe: , List-Post: List-Help: List-Subscribe: , Sender: xen-devel-bounces@lists.xen.org Errors-To: xen-devel-bounces@lists.xen.org To: Andrew Cooper Cc: xen-devel@lists.xen.org List-Id: xen-devel@lists.xenproject.org --===============3633803858675574930== Content-Type: multipart/alternative; boundary=e89a8fb1efa4f7ac5604c9567e47 --e89a8fb1efa4f7ac5604c9567e47 Content-Type: text/plain; charset=ISO-8859-1 Are you sure? 0f:10.0 is probably the physical function which you must > keep in dom0. > > ~Andrew > I find from xm pci-list-assignable-devices that 0f:10.0 is available - it is also hidden from dom0 (using pciback.hide in kernel arguments) if that is not the case, which physical function i can assign to domU? i tried with 0f:11.6, and others too, but i got similar messages. > > > i attach 0f:10.0 to a domU ubuntu machine, xm pci-attach ubuntu 0f:10.0 > > on my dom0 machine, i can ping other machine using eth2, (implying PF on > eth2 is active) > > on my domU machine, when i attach the virtual function, i get the > following messages > > [ 2282.688356] ixgbevf 0000:00:00.0: Xen PCI mapped GSI0 to IRQ28 > [ 2282.688470] ixgbevf 0000:00:00.0: setting latency timer to 64 > [ 2282.690187] ixgbevf 0000:00:00.0: PF still in reset state, assigning > new address > > while PF on eth2 is there and active, since i can ping other machine. > > Now, when I try to bring up the VF interface on domU, > i get the following error > > 2476.295582] Unable to start - perhaps the PF Driver isn't up yet > SIOCSIFFLAGS: Network is down > [ 2476.296917] Unable to start - perhaps the PF Driver isn't up yet > SIOCSIFFLAGS: Network is down > > and on dmesg on domU, > [ 2476.295582] Unable to start - perhaps the PF Driver isn't up yet > [ 2476.296917] Unable to start - perhaps the PF Driver isn't up yet > > > Any thoughts on what could be wrong? I have been struggling with this > for quite some time > and would really appreciate your thoughts on it. > > Thanks, > Ashok > > > > > > > > -- > Andrew Cooper - Dom0 Kernel Engineer, Citrix XenServer > T: +44 (0)1223 225 900, http://www.citrix.com > > > _______________________________________________ > Xen-devel mailing list > Xen-devel@lists.xen.org > http://lists.xen.org/xen-devel > > --e89a8fb1efa4f7ac5604c9567e47 Content-Type: text/html; charset=ISO-8859-1 Content-Transfer-Encoding: quoted-printable

Are you sure?=A0 0f:10.0 is probably the physical function which you must keep in dom0.

~Andrew

I find from xm pci-list-a= ssignable-devices =A0that 0f:10.0 is available - it is also hidden from dom= 0 (using pciback.hide in kernel arguments)

if that= is not the case, which physical function i can assign to domU?
i tried with 0f:11.6, and others too, but i got similar messages.




i attach 0f:10.0 to a domU ubuntu machine,=A0xm pci-attach ubuntu 0f:10.0

on my dom0 machine, i can ping other machine using eth2, (implying PF on eth2 is active)

on my domU machine, when i attach the virtual function, i get the following messages

[ 2282.688356] ixgbevf 0000:00:00.0: Xen PCI mapped GSI0 to IRQ28
[ 2282.688470] ixgbevf 0000:00:00.0: setting latency timer to 64
[ 2282.690187] ixgbevf 0000:00:00.0: PF still in reset state, assigning new address

while PF on eth2 is =A0there and active, since i can ping other machine.

Now, when I try to bring up the VF interface on domU,=A0
=A0i get the following error

=A02476.295582] Unable to start - perhaps the PF Driver isn't up yet
SIOCSIFFLAGS: Network is down
[ 2476.296917] Unable to start - perhaps the PF Driver isn't up yet
SIOCSIFFLAGS: Network is down

and on dmesg on domU,=A0
[ 2476.295582] Unable to start - perhaps the PF Driver isn't up yet
[ 2476.296917] Unable to start - perhaps the PF Driver isn't up yet


Any thoughts on what could be wrong? I have been struggling with this for quite some time
and would really appreciate your thoughts on it.

Thanks,=A0
Ashok







-=
-=20
Andrew Cooper - Dom0 Kernel Engineer, Citrix XenServer
T: +44 (0)1223 225 900, http://www.citrix.com

_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xen.org
http://lists.x= en.org/xen-devel


--e89a8fb1efa4f7ac5604c9567e47-- --===============3633803858675574930== Content-Type: text/plain; charset="us-ascii" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit Content-Disposition: inline _______________________________________________ Xen-devel mailing list Xen-devel@lists.xen.org http://lists.xen.org/xen-devel --===============3633803858675574930==-- From mboxrd@z Thu Jan 1 00:00:00 1970 From: Andrew Cooper Subject: Re: issue using SRIOV "Unable to start - perhaps the PF driver is not up yet", while PF driver is actually up Date: Mon, 10 Sep 2012 11:38:44 +0100 Message-ID: <504DC334.6060201@citrix.com> References: <504DC059.4070003@citrix.com> Mime-Version: 1.0 Content-Type: multipart/mixed; boundary="===============7699979477034878547==" Return-path: In-Reply-To: List-Unsubscribe: , List-Post: List-Help: List-Subscribe: , Sender: xen-devel-bounces@lists.xen.org Errors-To: xen-devel-bounces@lists.xen.org To: Ashok Anand Cc: "xen-devel@lists.xen.org" List-Id: xen-devel@lists.xenproject.org --===============7699979477034878547== Content-Type: multipart/alternative; boundary="------------090908030301000108080305" --------------090908030301000108080305 Content-Type: text/plain; charset="ISO-8859-1" Content-Transfer-Encoding: 7bit On 10/09/12 11:34, Ashok Anand wrote: > > > Are you sure? 0f:10.0 is probably the physical function which you > must keep in dom0. > > ~Andrew > > > I find from xm pci-list-assignable-devices that 0f:10.0 is available > - it is also hidden from dom0 (using pciback.hide in kernel arguments) > > if that is not the case, which physical function i can assign to domU? > i tried with 0f:11.6, and others too, but i got similar messages. What does lspci -vv for the physical function say? As for the physical function: it is unsafe to pass physical functions to a non-trusted guest, as the physical function has complete control over the all the virtual functions, even if they are passed through to other guests. For that reason, the physical function should remain in dom0 (or a device driver domain if you are going for disaggregation). > > > >> >> i attach 0f:10.0 to a domU ubuntu machine, xm pci-attach ubuntu >> 0f:10.0 >> >> on my dom0 machine, i can ping other machine using eth2, >> (implying PF on eth2 is active) >> >> on my domU machine, when i attach the virtual function, i get the >> following messages >> >> [ 2282.688356 ] ixgbevf 0000:00:00.0: Xen >> PCI mapped GSI0 to IRQ28 >> [ 2282.688470 ] ixgbevf 0000:00:00.0: >> setting latency timer to 64 >> [ 2282.690187 ] ixgbevf 0000:00:00.0: PF >> still in reset state, assigning new address >> >> while PF on eth2 is there and active, since i can ping other >> machine. >> >> Now, when I try to bring up the VF interface on domU, >> i get the following error >> >> 2476.295582] Unable to start - perhaps the PF Driver isn't up yet >> SIOCSIFFLAGS: Network is down >> [ 2476.296917] Unable to start - perhaps the PF Driver isn't up yet >> SIOCSIFFLAGS: Network is down >> >> and on dmesg on domU, >> [ 2476.295582] Unable to start - perhaps the PF Driver isn't up yet >> [ 2476.296917] Unable to start - perhaps the PF Driver isn't up yet >> >> >> Any thoughts on what could be wrong? I have been struggling with >> this for quite some time >> and would really appreciate your thoughts on it. >> >> Thanks, >> Ashok >> >> >> >> >> >> > > -- > Andrew Cooper - Dom0 Kernel Engineer, Citrix XenServer > T: +44 (0)1223 225 900 , http://www.citrix.com > > > _______________________________________________ > Xen-devel mailing list > Xen-devel@lists.xen.org > http://lists.xen.org/xen-devel > > -- Andrew Cooper - Dom0 Kernel Engineer, Citrix XenServer T: +44 (0)1223 225 900, http://www.citrix.com --------------090908030301000108080305 Content-Type: text/html; charset="ISO-8859-1" Content-Transfer-Encoding: 7bit On 10/09/12 11:34, Ashok Anand wrote:


Are you sure?  0f:10.0 is probably the physical function which you must keep in dom0.

~Andrew

I find from xm pci-list-assignable-devices  that 0f:10.0 is available - it is also hidden from dom0 (using pciback.hide in kernel arguments)

if that is not the case, which physical function i can assign to domU?
i tried with 0f:11.6, and others too, but i got similar messages.

What does lspci -vv for the physical function say?

As for the physical function: it is unsafe to pass physical functions to a non-trusted guest, as the physical function has complete control over the all the virtual functions, even if they are passed through to other guests.  For that reason, the physical function should remain in dom0 (or a device driver domain if you are going for disaggregation).





i attach 0f:10.0 to a domU ubuntu machine, xm pci-attach ubuntu 0f:10.0

on my dom0 machine, i can ping other machine using eth2, (implying PF on eth2 is active)

on my domU machine, when i attach the virtual function, i get the following messages

[ 2282.688356] ixgbevf 0000:00:00.0: Xen PCI mapped GSI0 to IRQ28
[ 2282.688470] ixgbevf 0000:00:00.0: setting latency timer to 64
[ 2282.690187] ixgbevf 0000:00:00.0: PF still in reset state, assigning new address

while PF on eth2 is  there and active, since i can ping other machine.

Now, when I try to bring up the VF interface on domU, 
 i get the following error

 2476.295582] Unable to start - perhaps the PF Driver isn't up yet
SIOCSIFFLAGS: Network is down
[ 2476.296917] Unable to start - perhaps the PF Driver isn't up yet
SIOCSIFFLAGS: Network is down

and on dmesg on domU, 
[ 2476.295582] Unable to start - perhaps the PF Driver isn't up yet
[ 2476.296917] Unable to start - perhaps the PF Driver isn't up yet


Any thoughts on what could be wrong? I have been struggling with this for quite some time
and would really appreciate your thoughts on it.

Thanks, 
Ashok







-- 
Andrew Cooper - Dom0 Kernel Engineer, Citrix XenServer
T: +44 (0)1223 225 900, http://www.citrix.com

_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xen.org
http://lists.xen.org/xen-devel



-- 
Andrew Cooper - Dom0 Kernel Engineer, Citrix XenServer
T: +44 (0)1223 225 900, http://www.citrix.com
--------------090908030301000108080305-- --===============7699979477034878547== Content-Type: text/plain; charset="us-ascii" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit Content-Disposition: inline _______________________________________________ Xen-devel mailing list Xen-devel@lists.xen.org http://lists.xen.org/xen-devel --===============7699979477034878547==-- From mboxrd@z Thu Jan 1 00:00:00 1970 From: Ashok Anand Subject: Re: issue using SRIOV "Unable to start - perhaps the PF driver is not up yet", while PF driver is actually up Date: Mon, 10 Sep 2012 16:16:47 +0530 Message-ID: References: <504DC059.4070003@citrix.com> <504DC334.6060201@citrix.com> Mime-Version: 1.0 Content-Type: multipart/mixed; boundary="===============3163611272199496851==" Return-path: In-Reply-To: <504DC334.6060201@citrix.com> List-Unsubscribe: , List-Post: List-Help: List-Subscribe: , Sender: xen-devel-bounces@lists.xen.org Errors-To: xen-devel-bounces@lists.xen.org To: Andrew Cooper Cc: "xen-devel@lists.xen.org" List-Id: xen-devel@lists.xenproject.org --===============3163611272199496851== Content-Type: multipart/alternative; boundary=e89a8fb1ffc2a69dac04c956ac5c --e89a8fb1ffc2a69dac04c956ac5c Content-Type: text/plain; charset=ISO-8859-1 I am passing virtual functions. please see below ,based on the message from lspci. > What does lspci -vv for the physical function say? > > As for the physical function: it is unsafe to pass physical functions to a > non-trusted guest, as the physical function has complete control over the > all the virtual functions, even if they are passed through to other > guests. For that reason, the physical function should remain in dom0 (or a > device driver domain if you are going for disaggregation). > here is the message lspci -vv | grep Eth gives me, 0f:00.0 Ethernet controller: Intel Corporation 82599EB 10-Gigabit SFI/SFP+ Network Connection (rev 01) Subsystem: Intel Corporation Ethernet Server Adapter X520-2 0f:00.1 Ethernet controller: Intel Corporation 82599EB 10-Gigabit SFI/SFP+ Network Connection (rev 01) Subsystem: Intel Corporation Ethernet Server Adapter X520-2 0f:10.0 Ethernet controller: Intel Corporation 82599 Ethernet Controller Virtual Function (rev 01) 0f:10.2 Ethernet controller: Intel Corporation 82599 Ethernet Controller Virtual Function (rev 01) 0f:10.4 Ethernet controller: Intel Corporation 82599 Ethernet Controller Virtual Function (rev 01) 0f:10.6 Ethernet controller: Intel Corporation 82599 Ethernet Controller Virtual Function (rev 01) 0f:11.0 Ethernet controller: Intel Corporation 82599 Ethernet Controller Virtual Function (rev 01) 0f:11.2 Ethernet controller: Intel Corporation 82599 Ethernet Controller Virtual Function (rev 01) 0f:11.4 Ethernet controller: Intel Corporation 82599 Ethernet Controller Virtual Function (rev 01) 0f:11.6 Ethernet controller: Intel Corporation 82599 Ethernet Controller Virtual Function (rev 01) Here, 0f:00.0 is the physical function, while 0f:10.0 and others are virtual functions -- so I am attaching virtual functions. > > > > >> >> >> i attach 0f:10.0 to a domU ubuntu machine, xm pci-attach ubuntu 0f:10.0 >> >> on my dom0 machine, i can ping other machine using eth2, (implying PF >> on eth2 is active) >> >> on my domU machine, when i attach the virtual function, i get the >> following messages >> >> [ 2282.688356 <%5B%202282.688356>] ixgbevf 0000:00:00.0: Xen PCI mapped >> GSI0 to IRQ28 >> [ 2282.688470 <%5B%202282.688470>] ixgbevf 0000:00:00.0: setting latency >> timer to 64 >> [ 2282.690187 <%5B%202282.690187>] ixgbevf 0000:00:00.0: PF still in >> reset state, assigning new address >> >> while PF on eth2 is there and active, since i can ping other machine. >> >> Now, when I try to bring up the VF interface on domU, >> i get the following error >> >> 2476.295582] Unable to start - perhaps the PF Driver isn't up yet >> SIOCSIFFLAGS: Network is down >> [ 2476.296917] Unable to start - perhaps the PF Driver isn't up yet >> SIOCSIFFLAGS: Network is down >> >> and on dmesg on domU, >> [ 2476.295582] Unable to start - perhaps the PF Driver isn't up yet >> [ 2476.296917] Unable to start - perhaps the PF Driver isn't up yet >> >> >> Any thoughts on what could be wrong? I have been struggling with this >> for quite some time >> and would really appreciate your thoughts on it. >> >> Thanks, >> Ashok >> >> >> >> >> >> >> >> -- >> Andrew Cooper - Dom0 Kernel Engineer, Citrix XenServer >> T: +44 (0)1223 225 900, http://www.citrix.com >> >> >> _______________________________________________ >> Xen-devel mailing list >> Xen-devel@lists.xen.org >> http://lists.xen.org/xen-devel >> >> > > -- > Andrew Cooper - Dom0 Kernel Engineer, Citrix XenServer > T: +44 (0)1223 225 900, http://www.citrix.com > > --e89a8fb1ffc2a69dac04c956ac5c Content-Type: text/html; charset=ISO-8859-1 Content-Transfer-Encoding: quoted-printable

I am passing virtual functio= ns. please see below ,based on the message from lspci.=A0
What does lspci -vv for the physi= cal function say?

As for the physical function: it is unsafe to pass physical functions to a non-trusted guest, as the physical function has complete control over the all the virtual functions, even if they are passed through to other guests.=A0 For that reason, the physical function should remain in dom0 (or a device driver domain if you are going for disaggregation).

here i= s the message lspci -vv | grep Eth gives me,=A0

0f:00.0 Ethernet controller: Intel Corporation 82599EB 10-Gigabit SFI/SF= P+ Network Connection (rev 01)
Subsy= stem: Intel Corporation Ethernet Server Adapter X520-2
0f:00.1 Et= hernet controller: Intel Corporation 82599EB 10-Gigabit SFI/SFP+ Network Co= nnection (rev 01)
Subsy= stem: Intel Corporation Ethernet Server Adapter X520-2
0f:10.0 Et= hernet controller: Intel Corporation 82599 Ethernet Controller Virtual Func= tion (rev 01)
0f:10.2 Ethernet controller: Intel Corporation 82599 Ethernet Controll= er Virtual Function (rev 01)
0f:10.4 Ethernet controller: Intel C= orporation 82599 Ethernet Controller Virtual Function (rev 01)
0f:10.6 Ethernet controller: Intel Corporation 82599 Ethernet Controller Vi= rtual Function (rev 01)
0f:11.0 Ethernet controller: Intel Corpor= ation 82599 Ethernet Controller Virtual Function (rev 01)
0f:11.2= Ethernet controller: Intel Corporation 82599 Ethernet Controller Virtual F= unction (rev 01)
0f:11.4 Ethernet controller: Intel Corporation 82599 Ethernet Controll= er Virtual Function (rev 01)
0f:11.6 Ethernet controller: Intel C= orporation 82599 Ethernet Controller Virtual Function (rev 01)

Here, 0f:00.0 is the physical function, while 0f:10.0 a= nd others are virtual functions -- so I am attaching virtual functions.=A0<= /div>


=A0






i attach 0f:10.0 to a domU ubuntu machine,=A0xm pci-attach ubuntu 0f:10.0

on my dom0 machine, i can ping other machine using eth2, (implying PF on eth2 is active)

on my domU machine, when i attach the virtual function, i get the following messages

[ 2282.688356] ixgbevf 0000:00:00.0: Xen PCI mapped GSI0 to IRQ28
[ 2282.688470] ixgbevf 0000:00:00.0: setting latency timer to 64
[ 2282.690187] ixgbevf 0000:00:00.0: PF still in reset state, assigning new address

while PF on eth2 is =A0there and active, since i can ping other machine.

Now, when I try to bring up the VF interface on domU,=A0
=A0i get the following error

=A02476.295582] Unable to start - perhaps the PF Driver isn't up yet
SIOCSIFFLAGS: Network is down
[ 2476.296917] Unable to start - perhaps the PF Driver isn't up yet
SIOCSIFFLAGS: Network is down

and on dmesg on domU,=A0
[ 2476.295582] Unable to start - perhaps the PF Driver isn't up yet
[ 2476.296917] Unable to start - perhaps the PF Driver isn't up yet


Any thoughts on what could be wrong? I have been struggling with this for quite some time
and would really appreciate your thoughts on it.

Thanks,=A0
Ashok







--=20
Andrew Cooper - Dom0 Kernel Engineer, Citrix XenServer
T: +44 (0)1223 225 900, http://www.citrix.com

_______________________________________________
Xen-devel mailing list
Xen-= devel@lists.xen.org
http= ://lists.xen.org/xen-devel



--=20
Andrew Cooper - Dom0 Kernel Engineer, Citrix XenServer
T: +44 (0)1223 225 900, http://www.citrix.com

--e89a8fb1ffc2a69dac04c956ac5c-- --===============3163611272199496851== Content-Type: text/plain; charset="us-ascii" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit Content-Disposition: inline _______________________________________________ Xen-devel mailing list Xen-devel@lists.xen.org http://lists.xen.org/xen-devel --===============3163611272199496851==-- From mboxrd@z Thu Jan 1 00:00:00 1970 From: Ashok Anand Subject: Re: issue using SRIOV "Unable to start - perhaps the PF driver is not up yet", while PF driver is actually up Date: Tue, 11 Sep 2012 00:02:47 +0530 Message-ID: References: <504DC059.4070003@citrix.com> <504DC334.6060201@citrix.com> Mime-Version: 1.0 Content-Type: multipart/mixed; boundary="===============8874624558075012550==" Return-path: In-Reply-To: List-Unsubscribe: , List-Post: List-Help: List-Subscribe: , Sender: xen-devel-bounces@lists.xen.org Errors-To: xen-devel-bounces@lists.xen.org To: Andrew Cooper Cc: "xen-devel@lists.xen.org" List-Id: xen-devel@lists.xenproject.org --===============8874624558075012550== Content-Type: multipart/alternative; boundary=001517478a522e908004c95d2fd3 --001517478a522e908004c95d2fd3 Content-Type: text/plain; charset=ISO-8859-1 Any more thoughts on it? I will really appreciate it. regards, Ashok On Mon, Sep 10, 2012 at 4:16 PM, Ashok Anand wrote: > > I am passing virtual functions. please see below ,based on the message > from lspci. > >> What does lspci -vv for the physical function say? >> >> As for the physical function: it is unsafe to pass physical functions to >> a non-trusted guest, as the physical function has complete control over the >> all the virtual functions, even if they are passed through to other >> guests. For that reason, the physical function should remain in dom0 (or a >> device driver domain if you are going for disaggregation). >> > > here is the message lspci -vv | grep Eth gives me, > > 0f:00.0 Ethernet controller: Intel Corporation 82599EB 10-Gigabit SFI/SFP+ > Network Connection (rev 01) > Subsystem: Intel Corporation Ethernet Server Adapter X520-2 > 0f:00.1 Ethernet controller: Intel Corporation 82599EB 10-Gigabit SFI/SFP+ > Network Connection (rev 01) > Subsystem: Intel Corporation Ethernet Server Adapter X520-2 > 0f:10.0 Ethernet controller: Intel Corporation 82599 Ethernet Controller > Virtual Function (rev 01) > 0f:10.2 Ethernet controller: Intel Corporation 82599 Ethernet Controller > Virtual Function (rev 01) > 0f:10.4 Ethernet controller: Intel Corporation 82599 Ethernet Controller > Virtual Function (rev 01) > 0f:10.6 Ethernet controller: Intel Corporation 82599 Ethernet Controller > Virtual Function (rev 01) > 0f:11.0 Ethernet controller: Intel Corporation 82599 Ethernet Controller > Virtual Function (rev 01) > 0f:11.2 Ethernet controller: Intel Corporation 82599 Ethernet Controller > Virtual Function (rev 01) > 0f:11.4 Ethernet controller: Intel Corporation 82599 Ethernet Controller > Virtual Function (rev 01) > 0f:11.6 Ethernet controller: Intel Corporation 82599 Ethernet Controller > Virtual Function (rev 01) > > Here, 0f:00.0 is the physical function, while 0f:10.0 and others are > virtual functions -- so I am attaching virtual functions. > > > > >> >> >> >> >>> >>> >>> i attach 0f:10.0 to a domU ubuntu machine, xm pci-attach ubuntu 0f:10.0 >>> >>> on my dom0 machine, i can ping other machine using eth2, (implying PF >>> on eth2 is active) >>> >>> on my domU machine, when i attach the virtual function, i get the >>> following messages >>> >>> [ 2282.688356 <%5B%202282.688356>] ixgbevf 0000:00:00.0: Xen PCI >>> mapped GSI0 to IRQ28 >>> [ 2282.688470 <%5B%202282.688470>] ixgbevf 0000:00:00.0: setting >>> latency timer to 64 >>> [ 2282.690187 <%5B%202282.690187>] ixgbevf 0000:00:00.0: PF still in >>> reset state, assigning new address >>> >>> while PF on eth2 is there and active, since i can ping other machine. >>> >>> Now, when I try to bring up the VF interface on domU, >>> i get the following error >>> >>> 2476.295582] Unable to start - perhaps the PF Driver isn't up yet >>> SIOCSIFFLAGS: Network is down >>> [ 2476.296917] Unable to start - perhaps the PF Driver isn't up yet >>> SIOCSIFFLAGS: Network is down >>> >>> and on dmesg on domU, >>> [ 2476.295582] Unable to start - perhaps the PF Driver isn't up yet >>> [ 2476.296917] Unable to start - perhaps the PF Driver isn't up yet >>> >>> >>> Any thoughts on what could be wrong? I have been struggling with this >>> for quite some time >>> and would really appreciate your thoughts on it. >>> >>> Thanks, >>> Ashok >>> >>> >>> >>> >>> >>> >>> >>> -- >>> Andrew Cooper - Dom0 Kernel Engineer, Citrix XenServer >>> T: +44 (0)1223 225 900, http://www.citrix.com >>> >>> >>> _______________________________________________ >>> Xen-devel mailing list >>> Xen-devel@lists.xen.org >>> http://lists.xen.org/xen-devel >>> >>> >> >> -- >> Andrew Cooper - Dom0 Kernel Engineer, Citrix XenServer >> T: +44 (0)1223 225 900, http://www.citrix.com >> >> > --001517478a522e908004c95d2fd3 Content-Type: text/html; charset=ISO-8859-1 Content-Transfer-Encoding: quoted-printable Any more thoughts on it? I will really appreciate it.

re= gards,
Ashok

On Mon, Sep 10, 20= 12 at 4:16 PM, Ashok Anand <ashok.anand@gmail.com> wrote= :

I am passing virtual functions. please see below ,based on the message f= rom lspci.=A0
What does lspci -vv for the physi= cal function say?

As for the physical function: it is unsafe to pass physical functions to a non-trusted guest, as the physical function has complete control over the all the virtual functions, even if they are passed through to other guests.=A0 For that reason, the physical function should remain in dom0 (or a device driver domain if you are going for disaggregation).

= here is the message lspci -vv | grep Eth gives me,=A0

<= div>
0f:00.0 Ethernet controller: Intel Corporation 82599EB 10-Gigabit = SFI/SFP+ Network Connection (rev 01)
Subsystem: Intel Corporat= ion Ethernet Server Adapter X520-2
0f:00.1 Ethernet controller: I= ntel Corporation 82599EB 10-Gigabit SFI/SFP+ Network Connection (rev 01)
Subsystem: Intel Corporat= ion Ethernet Server Adapter X520-2
0f:10.0 Ethernet controller: I= ntel Corporation 82599 Ethernet Controller Virtual Function (rev 01)
0f:10.2 Ethernet controller: Intel Corporation 82599 Ethernet Controll= er Virtual Function (rev 01)
0f:10.4 Ethernet controller: Intel C= orporation 82599 Ethernet Controller Virtual Function (rev 01)
0f:10.6 Ethernet controller: Intel Corporation 82599 Ethernet Controller Vi= rtual Function (rev 01)
0f:11.0 Ethernet controller: Intel Corpor= ation 82599 Ethernet Controller Virtual Function (rev 01)
0f:11.2= Ethernet controller: Intel Corporation 82599 Ethernet Controller Virtual F= unction (rev 01)
0f:11.4 Ethernet controller: Intel Corporation 82599 Ethernet Controll= er Virtual Function (rev 01)
0f:11.6 Ethernet controller: Intel C= orporation 82599 Ethernet Controller Virtual Function (rev 01)

Here, 0f:00.0 is the physical function, while 0f:10.0 a= nd others are virtual functions -- so I am attaching virtual functions.=A0<= /div>


=A0






i attach 0f:10.0 to a domU ubuntu machine,=A0xm pci-attach ubuntu 0f:10.0

on my dom0 machine, i can ping other machine using eth2, (implying PF on eth2 is active)

on my domU machine, when i attach the virtual function, i get the following messages

[ 2282.688356] ixgbevf 0000:00:00.0: Xen PCI mapped GSI0 to IRQ28
[ 2282.688470] ixgbevf 0000:00:00.0: setting latency timer to 64
[ 2282.690187] ixgbevf 0000:00:00.0: PF still in reset state, assigning new address

while PF on eth2 is =A0there and active, since i can ping other machine.

Now, when I try to bring up the VF interface on domU,=A0
=A0i get the following error

=A02476.295582] Unable to start - perhaps the PF Driver isn't up yet
SIOCSIFFLAGS: Network is down
[ 2476.296917] Unable to start - perhaps the PF Driver isn't up yet
SIOCSIFFLAGS: Network is down

and on dmesg on domU,=A0
[ 2476.295582] Unable to start - perhaps the PF Driver isn't up yet
[ 2476.296917] Unable to start - perhaps the PF Driver isn't up yet


Any thoughts on what could be wrong? I have been struggling with this for quite some time
and would really appreciate your thoughts on it.

Thanks,=A0
Ashok







--=20
Andrew Cooper - Dom0 Kernel Engineer, Citrix XenServer
T: +44 (0)1223 225 900, http://www.citrix.com

_______________________________________________
Xen-devel mailing list
Xen-= devel@lists.xen.org
http= ://lists.xen.org/xen-devel



--=20
Andrew Cooper - Dom0 Kernel Engineer, Citrix XenServer
T: +44 (0)1223 225 900, http://www.citrix.com


--001517478a522e908004c95d2fd3-- --===============8874624558075012550== Content-Type: text/plain; charset="us-ascii" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit Content-Disposition: inline _______________________________________________ Xen-devel mailing list Xen-devel@lists.xen.org http://lists.xen.org/xen-devel --===============8874624558075012550==-- From mboxrd@z Thu Jan 1 00:00:00 1970 From: Andrew Cooper Subject: Re: issue using SRIOV "Unable to start - perhaps the PF driver is not up yet", while PF driver is actually up Date: Tue, 11 Sep 2012 10:32:25 +0100 Message-ID: <504F0529.7010204@citrix.com> References: <504DC059.4070003@citrix.com> <504DC334.6060201@citrix.com> Mime-Version: 1.0 Content-Type: multipart/mixed; boundary="===============0887041430581390211==" Return-path: In-Reply-To: List-Unsubscribe: , List-Post: List-Help: List-Subscribe: , Sender: xen-devel-bounces@lists.xen.org Errors-To: xen-devel-bounces@lists.xen.org To: xen-devel@lists.xen.org List-Id: xen-devel@lists.xenproject.org --===============0887041430581390211== Content-Type: multipart/alternative; boundary="------------030307030407000205090902" --------------030307030407000205090902 Content-Type: text/plain; charset="ISO-8859-1" Content-Transfer-Encoding: 7bit On 10/09/12 19:32, Ashok Anand wrote: > Any more thoughts on it? I will really appreciate it. Sorry - I am debugging a memory corruption issue, so not paying too close attention to emails. Have you ensured that the pif is up in dom0 before trying to use a vif? ~Andrew > > regards, > Ashok > > On Mon, Sep 10, 2012 at 4:16 PM, Ashok Anand > wrote: > > > I am passing virtual functions. please see below ,based on the > message from lspci. > > What does lspci -vv for the physical function say? > > As for the physical function: it is unsafe to pass physical > functions to a non-trusted guest, as the physical function has > complete control over the all the virtual functions, even if > they are passed through to other guests. For that reason, the > physical function should remain in dom0 (or a device driver > domain if you are going for disaggregation). > > > here is the message lspci -vv | grep Eth gives me, > > 0f:00.0 Ethernet controller: Intel Corporation 82599EB 10-Gigabit > SFI/SFP+ Network Connection (rev 01) > Subsystem: Intel Corporation Ethernet Server Adapter X520-2 > 0f:00.1 Ethernet controller: Intel Corporation 82599EB 10-Gigabit > SFI/SFP+ Network Connection (rev 01) > Subsystem: Intel Corporation Ethernet Server Adapter X520-2 > 0f:10.0 Ethernet controller: Intel Corporation 82599 Ethernet > Controller Virtual Function (rev 01) > 0f:10.2 Ethernet controller: Intel Corporation 82599 Ethernet > Controller Virtual Function (rev 01) > 0f:10.4 Ethernet controller: Intel Corporation 82599 Ethernet > Controller Virtual Function (rev 01) > 0f:10.6 Ethernet controller: Intel Corporation 82599 Ethernet > Controller Virtual Function (rev 01) > 0f:11.0 Ethernet controller: Intel Corporation 82599 Ethernet > Controller Virtual Function (rev 01) > 0f:11.2 Ethernet controller: Intel Corporation 82599 Ethernet > Controller Virtual Function (rev 01) > 0f:11.4 Ethernet controller: Intel Corporation 82599 Ethernet > Controller Virtual Function (rev 01) > 0f:11.6 Ethernet controller: Intel Corporation 82599 Ethernet > Controller Virtual Function (rev 01) > > Here, 0f:00.0 is the physical function, while 0f:10.0 and others > are virtual functions -- so I am attaching virtual functions. > > > > > > >> >> >> >>> >>> i attach 0f:10.0 to a domU ubuntu machine, xm pci-attach >>> ubuntu 0f:10.0 >>> >>> on my dom0 machine, i can ping other machine using eth2, >>> (implying PF on eth2 is active) >>> >>> on my domU machine, when i attach the virtual function, >>> i get the following messages >>> >>> [ 2282.688356 ] ixgbevf >>> 0000:00:00.0: Xen PCI mapped GSI0 to IRQ28 >>> [ 2282.688470 ] ixgbevf >>> 0000:00:00.0: setting latency timer to 64 >>> [ 2282.690187 ] ixgbevf >>> 0000:00:00.0: PF still in reset state, assigning new address >>> >>> while PF on eth2 is there and active, since i can ping >>> other machine. >>> >>> Now, when I try to bring up the VF interface on domU, >>> i get the following error >>> >>> 2476.295582] Unable to start - perhaps the PF Driver >>> isn't up yet >>> SIOCSIFFLAGS: Network is down >>> [ 2476.296917] Unable to start - perhaps the PF Driver >>> isn't up yet >>> SIOCSIFFLAGS: Network is down >>> >>> and on dmesg on domU, >>> [ 2476.295582] Unable to start - perhaps the PF Driver >>> isn't up yet >>> [ 2476.296917] Unable to start - perhaps the PF Driver >>> isn't up yet >>> >>> >>> Any thoughts on what could be wrong? I have been >>> struggling with this for quite some time >>> and would really appreciate your thoughts on it. >>> >>> Thanks, >>> Ashok >>> >>> >>> >>> >>> >>> >> >> -- >> Andrew Cooper - Dom0 Kernel Engineer, Citrix XenServer >> T: +44 (0)1223 225 900 , http://www.citrix.com >> >> >> _______________________________________________ >> Xen-devel mailing list >> Xen-devel@lists.xen.org >> http://lists.xen.org/xen-devel >> >> > > -- > Andrew Cooper - Dom0 Kernel Engineer, Citrix XenServer > T: +44 (0)1223 225 900 , http://www.citrix.com > > > -- Andrew Cooper - Dom0 Kernel Engineer, Citrix XenServer T: +44 (0)1223 225 900, http://www.citrix.com --------------030307030407000205090902 Content-Type: text/html; charset="ISO-8859-1" Content-Transfer-Encoding: 7bit
On 10/09/12 19:32, Ashok Anand wrote:
Any more thoughts on it? I will really appreciate it.

Sorry - I am debugging a memory corruption issue, so not paying too close attention to emails.

Have you ensured that the pif is up in dom0 before trying to use a vif?

~Andrew


regards,
Ashok

On Mon, Sep 10, 2012 at 4:16 PM, Ashok Anand <ashok.anand@gmail.com> wrote:

I am passing virtual functions. please see below ,based on the message from lspci. 
What does lspci -vv for the physical function say?

As for the physical function: it is unsafe to pass physical functions to a non-trusted guest, as the physical function has complete control over the all the virtual functions, even if they are passed through to other guests.  For that reason, the physical function should remain in dom0 (or a device driver domain if you are going for disaggregation).

here is the message lspci -vv | grep Eth gives me, 

0f:00.0 Ethernet controller: Intel Corporation 82599EB 10-Gigabit SFI/SFP+ Network Connection (rev 01)
Subsystem: Intel Corporation Ethernet Server Adapter X520-2
0f:00.1 Ethernet controller: Intel Corporation 82599EB 10-Gigabit SFI/SFP+ Network Connection (rev 01)
Subsystem: Intel Corporation Ethernet Server Adapter X520-2
0f:10.0 Ethernet controller: Intel Corporation 82599 Ethernet Controller Virtual Function (rev 01)
0f:10.2 Ethernet controller: Intel Corporation 82599 Ethernet Controller Virtual Function (rev 01)
0f:10.4 Ethernet controller: Intel Corporation 82599 Ethernet Controller Virtual Function (rev 01)
0f:10.6 Ethernet controller: Intel Corporation 82599 Ethernet Controller Virtual Function (rev 01)
0f:11.0 Ethernet controller: Intel Corporation 82599 Ethernet Controller Virtual Function (rev 01)
0f:11.2 Ethernet controller: Intel Corporation 82599 Ethernet Controller Virtual Function (rev 01)
0f:11.4 Ethernet controller: Intel Corporation 82599 Ethernet Controller Virtual Function (rev 01)
0f:11.6 Ethernet controller: Intel Corporation 82599 Ethernet Controller Virtual Function (rev 01)

Here, 0f:00.0 is the physical function, while 0f:10.0 and others are virtual functions -- so I am attaching virtual functions. 


 






i attach 0f:10.0 to a domU ubuntu machine, xm pci-attach ubuntu 0f:10.0

on my dom0 machine, i can ping other machine using eth2, (implying PF on eth2 is active)

on my domU machine, when i attach the virtual function, i get the following messages

[ 2282.688356] ixgbevf 0000:00:00.0: Xen PCI mapped GSI0 to IRQ28
[ 2282.688470] ixgbevf 0000:00:00.0: setting latency timer to 64
[ 2282.690187] ixgbevf 0000:00:00.0: PF still in reset state, assigning new address

while PF on eth2 is  there and active, since i can ping other machine.

Now, when I try to bring up the VF interface on domU, 
 i get the following error

 2476.295582] Unable to start - perhaps the PF Driver isn't up yet
SIOCSIFFLAGS: Network is down
[ 2476.296917] Unable to start - perhaps the PF Driver isn't up yet
SIOCSIFFLAGS: Network is down

and on dmesg on domU, 
[ 2476.295582] Unable to start - perhaps the PF Driver isn't up yet
[ 2476.296917] Unable to start - perhaps the PF Driver isn't up yet


Any thoughts on what could be wrong? I have been struggling with this for quite some time
and would really appreciate your thoughts on it.

Thanks, 
Ashok







-- 
Andrew Cooper - Dom0 Kernel Engineer, Citrix XenServer
T: +44 (0)1223 225 900, http://www.citrix.com

_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xen.org
http://lists.xen.org/xen-devel



-- 
Andrew Cooper - Dom0 Kernel Engineer, Citrix XenServer
T: +44 (0)1223 225 900, http://www.citrix.com



-- 
Andrew Cooper - Dom0 Kernel Engineer, Citrix XenServer
T: +44 (0)1223 225 900, http://www.citrix.com
--------------030307030407000205090902-- --===============0887041430581390211== Content-Type: text/plain; charset="us-ascii" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit Content-Disposition: inline _______________________________________________ Xen-devel mailing list Xen-devel@lists.xen.org http://lists.xen.org/xen-devel --===============0887041430581390211==-- From mboxrd@z Thu Jan 1 00:00:00 1970 From: Pasi =?iso-8859-1?Q?K=E4rkk=E4inen?= Subject: Re: issue using SRIOV "Unable to start - perhaps the PF driver is not up yet", while PF driver is actually up Date: Tue, 11 Sep 2012 13:05:10 +0300 Message-ID: <20120911100510.GP8912@reaktio.net> References: <504DC059.4070003@citrix.com> <504DC334.6060201@citrix.com> <504F0529.7010204@citrix.com> Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Return-path: Content-Disposition: inline In-Reply-To: <504F0529.7010204@citrix.com> List-Unsubscribe: , List-Post: List-Help: List-Subscribe: , Sender: xen-devel-bounces@lists.xen.org Errors-To: xen-devel-bounces@lists.xen.org To: Andrew Cooper Cc: xen-devel@lists.xen.org List-Id: xen-devel@lists.xenproject.org On Tue, Sep 11, 2012 at 10:32:25AM +0100, Andrew Cooper wrote: > On 10/09/12 19:32, Ashok Anand wrote: > > Any more thoughts on it? I will really appreciate it. > > Sorry - I am debugging a memory corruption issue, so not paying too close > attention to emails. > > Have you ensured that the pif is up in dom0 before trying to use a vif? > Yes, "ifconfig ethX up" for the PF is required in dom0 before the VF works in the VM. -- Pasi > ~Andrew > > regards, > Ashok > > On Mon, Sep 10, 2012 at 4:16 PM, Ashok Anand <[1]ashok.anand@gmail.com> > wrote: > > I am passing virtual functions. please see below ,based on the message > from lspci. > > What does lspci -vv for the physical function say? > > As for the physical function: it is unsafe to pass physical > functions to a non-trusted guest, as the physical function has > complete control over the all the virtual functions, even if they > are passed through to other guests. For that reason, the physical > function should remain in dom0 (or a device driver domain if you are > going for disaggregation). > > here is the message lspci -vv | grep Eth gives me, > 0f:00.0 Ethernet controller: Intel Corporation 82599EB 10-Gigabit > SFI/SFP+ Network Connection (rev 01) > Subsystem: Intel Corporation Ethernet Server Adapter X520-2 > 0f:00.1 Ethernet controller: Intel Corporation 82599EB 10-Gigabit > SFI/SFP+ Network Connection (rev 01) > Subsystem: Intel Corporation Ethernet Server Adapter X520-2 > 0f:10.0 Ethernet controller: Intel Corporation 82599 Ethernet > Controller Virtual Function (rev 01) > 0f:10.2 Ethernet controller: Intel Corporation 82599 Ethernet > Controller Virtual Function (rev 01) > 0f:10.4 Ethernet controller: Intel Corporation 82599 Ethernet > Controller Virtual Function (rev 01) > 0f:10.6 Ethernet controller: Intel Corporation 82599 Ethernet > Controller Virtual Function (rev 01) > 0f:11.0 Ethernet controller: Intel Corporation 82599 Ethernet > Controller Virtual Function (rev 01) > 0f:11.2 Ethernet controller: Intel Corporation 82599 Ethernet > Controller Virtual Function (rev 01) > 0f:11.4 Ethernet controller: Intel Corporation 82599 Ethernet > Controller Virtual Function (rev 01) > 0f:11.6 Ethernet controller: Intel Corporation 82599 Ethernet > Controller Virtual Function (rev 01) > Here, 0f:00.0 is the physical function, while 0f:10.0 and others are > virtual functions -- so I am attaching virtual functions. > > > i attach 0f:10.0 to a domU ubuntu machine, xm pci-attach > ubuntu 0f:10.0 > on my dom0 machine, i can ping other machine using eth2, > (implying PF on eth2 is active) > on my domU machine, when i attach the virtual function, i get > the following messages > [2][ 2282.688356] ixgbevf 0000:00:00.0: Xen PCI mapped GSI0 to > IRQ28 > [3][ 2282.688470] ixgbevf 0000:00:00.0: setting latency timer > to 64 > [4][ 2282.690187] ixgbevf 0000:00:00.0: PF still in reset > state, assigning new address > while PF on eth2 is there and active, since i can ping other > machine. > Now, when I try to bring up the VF interface on domU, > i get the following error > 2476.295582] Unable to start - perhaps the PF Driver isn't up > yet > SIOCSIFFLAGS: Network is down > [ 2476.296917] Unable to start - perhaps the PF Driver isn't > up yet > SIOCSIFFLAGS: Network is down > and on dmesg on domU, > [ 2476.295582] Unable to start - perhaps the PF Driver isn't > up yet > [ 2476.296917] Unable to start - perhaps the PF Driver isn't > up yet > Any thoughts on what could be wrong? I have been struggling > with this for quite some time > and would really appreciate your thoughts on it. > Thanks, > Ashok > > -- > Andrew Cooper - Dom0 Kernel Engineer, Citrix XenServer > T: [5]+44 (0)1223 225 900, [6]http://www.citrix.com > > _______________________________________________ > Xen-devel mailing list > [7]Xen-devel@lists.xen.org > [8]http://lists.xen.org/xen-devel > > -- > Andrew Cooper - Dom0 Kernel Engineer, Citrix XenServer > T: [9]+44 (0)1223 225 900, [10]http://www.citrix.com > > -- > Andrew Cooper - Dom0 Kernel Engineer, Citrix XenServer > T: +44 (0)1223 225 900, [11]http://www.citrix.com > > References > > Visible links > 1. mailto:ashok.anand@gmail.com > 2. file:///tmp/tel:%5B%202282.688356 > 3. file:///tmp/tel:%5B%202282.688470 > 4. file:///tmp/tel:%5B%202282.690187 > 5. file:///tmp/tel:%2B44%20%280%291223%20225%20900 > 6. http://www.citrix.com/ > 7. mailto:Xen-devel@lists.xen.org > 8. http://lists.xen.org/xen-devel > 9. file:///tmp/tel:%2B44%20%280%291223%20225%20900 > 10. http://www.citrix.com/ > 11. http://www.citrix.com/ > _______________________________________________ > Xen-devel mailing list > Xen-devel@lists.xen.org > http://lists.xen.org/xen-devel